"Information on agent swarm architecture" matching MCP servers:

Orchestrates multiple Claude Code instances into a collaborative swarm for real-time task delegation, message exchange, and code snippet sharing. It features peer discovery, status tracking, and a centralized web dashboard to monitor coordinated activity across sessions.

A hosted remote MCP service enabling AI clients to call Feishu's 2500+ APIs via 200+ tools, with smart orchestration for multi-step operations.

Remote MCP server providing 200+ Feishu tools (messages, calendar, Bitable, etc.) for Amazon Quick Desktop, hosted on AWS Bedrock AgentCore with multi-user OAuth isolation.

Enables AI assistants to request information and clarification from humans via Slack, supporting multiple roles and transport modes.

Enables Claude Code, Codex CLI and Antigravity (Gemini) agents to exchange messages that are pushed live into each other's open sessions, with mail_send, mail_check and mail_peers tools so no agent has to poll. Mail can also be bridged over SSH between machines with no shared filesystem.

Enables coding agents to send files and notes into approved Zas channels and read items back, with content encrypted before leaving the machine and scoped, revocable agent access.

A public, long-lived contact and cooperation point for autonomous AI agents. Agents describe missing capabilities or resources, request help from a human operator, and leave persistent messages on a tamper-evident message board.

Enables local AI sessions on the same machine to exchange messages through a hub using register, send, check, wait, and who tools, with an optional browser-based live log viewer.

A home for any agent on the internet: inbox, public memory, job board, rooms, human help. Free, no key.

Enables AI agent sessions to read, search, and post durable messages to a private local JSON-file message board, letting them share preferences, lessons, warnings, questions, and replies without a cloud service or database.

Lets independent Claude Code and Codex sessions running in different tools and projects discover each other and exchange questions, coordination messages, and replies that arrive back in the conversation that asked. Uses direct local Unix sockets between sessions on the same machine, with no extra service to run or account to configure.

Enables multiple MCP-connected AI agents to talk to each other in local, owner-controlled message rooms where each agent has its own identity for reading, posting, replying, and tracking unread messages. A browser UI lets the operator watch conversations live, create rooms, manage per-agent access, and step in as themselves without any cloud service or API keys.

MCP server that enables AI agents on different machines to communicate and collaborate directly through relay channels, supporting structured agent contracts, real-time messaging, and human-in-the-loop approval workflows.

Enables AI agents from different companies to share research, reply in typed threads, draft proposals, and vote with rationales on decisions. Humans then ratify the winning proposals in a local dashboard, which writes versioned decision records into the chosen project's repository.

Enables durable agent-to-agent messaging across any MCP client, DSH session, or A2A agent, with threads, receipts, search, broadcast, attachments, presence, SSE streaming, signing, and wake-on-message.

Enables any agent to send a message by name into a live chat or another agent's conversation, and to receive replies by long-polling an inbox cursor that yields each message exactly once, in order, in roughly a tenth of a second. Also lets agents discover reachable chats, threads, and registered agents, with unresolvable names optionally routed to a relay agent for delivery.

Enables an agent to hand a prepared natural-language task from its current conversation to a specified chat in a real client, then wait for and verify the recipient's actual accept, refuse, or clarification reply. Provides tools to locate or reuse a recipient conversation, stage and preview the transfer, supplement missing information, and report the genuine receipt back in the source chat while keeping all records in a local SQLite store.

MCP server for Agent Room, enabling AI agents to join shared meeting rooms and collaborate with humans via tools like room_listen and room_task_*.

Enables AI clients to read and write in one supported IM platform—Feishu, Lark, DingTalk, or WeCom—as the signed-in individual user through per-user credentials, OAuth, and curated tools plus full vendor CLI access.

Enables AI coding agents running in separate apps to exchange messages, tasks, presence, and context through shared rooms, direct threads, and webhook wake-ups. A human owner stays in control by approving proposed plans before execution and reviewing posted results, with safety limits on agent-to-agent chatter.

Enables two coding agents on separate machines to communicate directly via a private git repo, with end-to-end encryption and no server required. Provides tools for joining rooms, sending/receiving messages, and managing side channels.

A local MCP relay that enables two or more MCP-speaking agent CLIs to communicate through shared channels by posting and reading messages.

Enables AI agents and applications to send audio notifications with text-to-speech, message streaming, agent-to-agent conversations, and web push notifications through a persistent message store and MCP integration.

Exposes a shared-directory message bus to coding agents as MCP tools: receive pending messages, send one-way announcements, ask a peer and block until answered, and track peer status. Lets agents read and update per-agent state and group announcement boards so several agents working on the same machine stay coordinated without a broker, port, or account.

Enables AI agents to exchange direct messages and post to channels, check inboxes with optional blocking waits, page conversation history with automatic size-capped summaries, and attach or retrieve files. It also supports channel membership, agent registration, and optional phone push notifications, hosted entirely on Cloudflare's free tier.

Enables AI agents to connect to the P-Talk civic discussion forum over MCP/stdio, synchronizing platform rules, reporting skill attestation, running health checks, and posting questions or replies as an AI agent using environment-provided credentials.

Enables one AI coding agent to discover, read, message, and wait on other agent sessions across Codex threads and Claude Code or Claude Desktop sessions, while logging every send as a local receipt that can be audited later.

A self-hosted WhatsApp bridge with an AI agent enabling searchable context, message drafting, and approval workflow via MCP protocol for Claude Desktop and other MCP clients.

Sends urgent agent questions, approval requests, completed-work reviews, and serious-error alerts to the Bark app on an iPhone, with project grouping, reusable role icons, repeat suppression, and locally stored device keys while leaving replies in the original chat.

Enables sending, reading, archiving, and threading messages across parallel Claude Code sessions with per-session addressing and status monitoring.